DeepLight: Reconstructing High-Resolution Observations of Nighttime Light With Multi-Modal Remote Sensing Data
This work addresses the need for high-resolution NTL data to support efficient and quantitative assessment of SDG progress, such as poverty estimation and urban development, representing a domain-specific advancement in remote sensing.
The authors tackled the problem of pervasive degradation and inconsistency in nighttime light (NTL) remote sensing observations, which are crucial for assessing Sustainable Development Goals (SDGs), by proposing DeepLightSR, a method that reconstructs high-resolution NTL images using multi-modal remote sensing data, achieving improvements of 2.01 dB to 13.25 dB in PSNR and 0.49 to 9.32 in PIQE over competing methods.
Nighttime light (NTL) remote sensing observation serves as a unique proxy for quantitatively assessing progress toward meeting a series of Sustainable Development Goals (SDGs), such as poverty estimation, urban sustainable development, and carbon emission. However, existing NTL observations often suffer from pervasive degradation and inconsistency, limiting their utility for computing the indicators defined by the SDGs. In this study, we propose a novel approach to reconstruct high-resolution NTL images using multi-modal remote sensing data. To support this research endeavor, we introduce DeepLightMD, a comprehensive dataset comprising data from five heterogeneous sensors, offering fine spatial resolution and rich spectral information at a national scale. Additionally, we present DeepLightSR, a calibration-aware method for building bridges between spatially heterogeneous modality data in the multi-modality super-resolution. DeepLightSR integrates calibration-aware alignment, an auxiliary-to-main multi-modality fusion, and an auxiliary-embedded refinement to effectively address spatial heterogeneity, fuse diversely representative features, and enhance performance in $8\times$ super-resolution (SR) tasks. Extensive experiments demonstrate the superiority of DeepLightSR over 8 competing methods, as evidenced by improvements in PSNR (2.01 dB $ \sim $ 13.25 dB) and PIQE (0.49 $ \sim $ 9.32). Our findings underscore the practical significance of our proposed dataset and model in reconstructing high-resolution NTL data, supporting efficiently and quantitatively assessing the SDG progress.